Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8282
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology related to court cases and petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciliation
    -0.67
    Хьажоргаш
    -0.61
    principalColumn
    -0.60
     kasarigan
    -0.58
    utilisons
    -0.57
    ✨:
    -0.57
    ymo
    -0.56
     Bohemia
    -0.56
     <=",
    -0.55
    uilla
    -0.55
    POSITIVE LOGITS
     Ohio
    1.25
    Ohio
    1.10
     Columbus
    1.08
     OHIO
    0.98
    Columbus
    0.94
     OSU
    0.88
    ohio
    0.83
     OH
    0.80
    umbus
    0.74
     Youngstown
    0.70
    Activations Density 0.175%

    No Known Activations